Skip to content
ModelListedExternal
Download

Whisper Th Medium Combined

This model is a fine-tuned version of openai/whisper-medium on augmented versions of the mozilla-foundation/commonvoice130 th, google/fleurs, and curated datasets. It achieves the following results on the...

Sourcehuggingface.co/Nawanop/whisper-th-medium-combined/tree/f3261c0999d6ca5cf519291d40d97a03af0db683
KindText modelBase modelopenai/whisper-mediumVersionFP16Bgrade

Model source

Kind
Text model
File size
1.52 GB
Base model
openai/whisper-medium
Version
vFP16
Updated
Oct 31, 2026
Downloads
8
Source
Hugging Face

Source description

Whisper Medium (Thai): Combined V3

This model is a fine-tuned version of openai/whisper-medium on augmented versions of the mozilla-foundation/common_voice_13_0 th, google/fleurs, and curated datasets. It achieves the following results on the common-voice-13 test set:

  • WER: 7.42 (with Deepcut Tokenizer)

Model description

Use the model with huggingface's transformers as follows:

from transformers import pipeline

MODEL_NAME = "biodatlab/whisper-th-medium-combined"  # specify the model name
lang = "th"  # change to Thai langauge

device = 0 if torch.cuda.is_available() else "cpu"

pipe = pipeline(
    task="automatic-speech-recognition",
    model=MODEL_NAME,
    chunk_length_s=30,
    device=device,
)
pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(
  language=lang,
  task="transcribe"
)
text = pipe("audio.mp3")["text"] # give audio mp3 and transcribe text

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 10000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.1.0
  • Datasets 2.16.1
  • Tokenizers 0.15.1

Citation

Cite using Bibtex:

@misc {thonburian_whisper_med,
    author       = { Atirut Boribalburephan, Zaw Htet Aung, Knot Pipatsrisawat, Titipat Achakulvisut },
    title        = { Thonburian Whisper: A fine-tuned Whisper model for Thai automatic speech recognition },
    year         = 2022,
    url          = { https://huggingface.co/biodatlab/whisper-th-medium-combined },
    doi          = { 10.57967/hf/0226 },
    publisher    = { Hugging Face }
}

Sources

1 source
Hugging FacePrimaryVersion f3261c0999d6ca5cf519291d40d97a03af0db683
huggingface.co/Nawanop/whisper-th-medium-combined/tree/f3261c0999d6ca5cf519291d40d97a03af0db683

Verified Oct 31

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

model.safetensors

safetensors · FP16 (unverified) · 1.52 GB · SHA-256 c683cd8930c6…97b1 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 15huggingface.co/Nawanop/whisper-th-medium-combined

--- language: - th license: apache-2.0 library_name: transformers tags: - whisper-event - generated_from_trainer datasets: - mozilla-foundation/common_voice_13_0 - google/fleurs metrics: - wer base_model: openai/whisper-medium model-index: - name: Whisper Medium Thai Combined V4 - biodatlab results: - task: type: automatic-speech-recognition name: Automatic Speech Recognition dataset: name: mozilla-foundation/common_voice_13_0 th type: mozilla-foundation/common_voice_13_0 config: th split: test args: th metrics: - type: wer value: 7.42 name: Wer --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Whisper Medium (Thai): Combined V3 This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on augmented versions of the mozilla-foundation/common_voice_13_0 th, google/fleurs, and curated datasets. It achieves the following results on the common-voice-13 test set: - WER: 7.42 (with Deepcut Tokenizer) ## Model description Use the model with huggingface's `transformers` as follows: ```py from transformers import pipeline MODEL_NAME = "biodatlab/whisper-th-medium-combined" # specify the model name lang = "th" # change to Thai langauge device = 0 if torch.cuda.is_available() else "cpu" pipe = pipeline( task="automatic-speech-recognition", model=MODEL_NAME, chunk_length_s=30, device=device, ) pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids( language=lang, task="transcribe" ) text = pipe("audio.mp3")["text"] # give audio mp3 and transcribe text ``` ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 10000 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.37.2 - Pytorch 2.1.0 - Datasets 2.16.1 - Tokenizers 0.15.1 ## Citation Cite using Bibtex: ``` @misc {thonburian_whisper_med, author = { Atirut Boribalbu...

NoteOct 31huggingface.co/Nawanop/whisper-th-medium-combined

Source context: 8 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo Nawanop/whisper-th-medium-combined

NoteAug 15huggingface.co/Nawanop/whisper-th-medium-combined

Source context: 12 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo Nawanop/whisper-th-medium-combined